mirror of
https://github.com/oobabooga/text-generation-webui.git
synced 2026-03-07 14:13:49 +01:00
Instead of two separate paths (format files vs Chat Template), all instruction training now uses apply_chat_template() with assistant-only label masking. Users pick a Jinja2 template from the dropdown or use the model's built-in chat template — both work identically. |
||
|---|---|---|
| .. | ||
| characters | ||
| extensions | ||
| grammars | ||
| image_models | ||
| instruction-templates | ||
| loras | ||
| mmproj | ||
| models | ||
| presets | ||
| training/datasets | ||
| users | ||
| CMD_FLAGS.txt | ||